Researchers observe first ‘near-autonomous’ AI attack on government target in Taiwan

Israeli cyber firm Dream said the framework adapted mid-operation, corrected its mistakes and expanded as it went along.

Suspected Chinese hackers used open-source artificial intelligence models to run a cyberattack against the Taiwanese government in the first publicly known case of an autonomous AI hack hitting a government target, according to research published Wednesday.

The hackers extracted more than 2,500 personnel records, among other data, in the “near-autonomous attack,” researchers at Israeli cyber firm Dream wrote in a blog post. The attackers set up the framework so that it could “adapt mid-operation without human intervention.”

The framework “implements dedicated research phases it calls ‘Learning Cycles’ — autonomous sessions where the AI system searches vulnerability databases, GitHub repositories, and security research publications for techniques specifically applicable to its target government’s infrastructure,” the post reads.

And then it kept going.

“The attacker didn’t stop at primary targets,” Dream said. “It expanded the operation to government IT supply chain vendors, a nuclear safety agency, a government email system, and 7+ energy sector companies — scanning them all in parallel for misconfigurations, exposed admin interfaces, and exploitable vulnerabilities.”

It also learned from its mistakes as it went on, Dream said in identifying what stood out about the campaign.

Autonomous AI-powered cyberattacks have raised alarms in the past: Anthropic reported last fall that it stopped the first autonomous cyber espionage campaign, although researchers noted that the “autonomous” campaign still required significant human work. 

The Financial Times first reported the Dream research and details on the target.

The hackers used two popular open-source AI frameworks, Hermes and OpenClaw, to set up the Taiwan operation. They bypassed safety guardrails by framing the work as authorized penetration testing, according to Dream.

The firm discovered the operation via an online archive of 160 megabytes and nearly 1,400 files, revealing “a multi-agent AI system that achieved confirmed, real-world compromises against state infrastructure.”

As with the autonomous cyber espionage campaign uncovered last fall, the attack Dream examined also noted the need for human tinkering.

“We increasingly see threat actors leveraging AI for autonomous offensive operations,” the company wrote. “But building a system that actually works at this level takes more work than ‘just’ running a model. It demands careful adjustment to the specific task, optimization of agent coordination, and fine-tuning of decision logic — the kind of sophistication evident in this framework’s Bayesian prioritization, self-correction loops, and adaptive research cycles.”

Government

• CIA’s Michael Ellis says cyber intelligence is changing how the agency operates

• The G7 tells industry to hurry up and prep for post-quantum encryption

• Jail time for Maine child in 764 marks turning point in federal law enforcement

• FCC proposes public scorecard to rate telecoms on anti-robocall efforts

Technology

• European parliament members call for slowdown of Serbia’s EU entry over spyware use

• Pegasus, NoviSpy variant spyware found on devices of Serbian activists

• Wyden seeks upgraded NSA security guidance on commercial VPN use

• The Collective Cyber Defense letter wrote your next vendor questionnaire

Threats

• Microsoft discloses two actively exploited zero-days among 974 vulnerabilities

• Russian national extradited to US for alleged involvement in bank-account takeover scheme

• Attackers exploit zero-days in consistently besieged SonicWall product

• Dogged Russia-based botnet dismantled after 23-year run

Policy

• Whistleblower says USPS deploying new, ‘untested’ IT systems governing mail-in ballots

• ‘Watershed 250’ test program in Texas looks to private sector for water cybersecurity help

• Former sexual abuse victims say Grok used their images, videos to train deepfake capabilities

• Cyber threats nudge Trump to sign executive order on foreign equipment in U.S. energy infrastructure